search

krumo / Domain-Adaptive-Faster-RCNN-PyTorch

Domain Adaptive Faster R-CNN in PyTorch
MIT License
305 stars 68 forks source link

This implementation is quit diffrent from the original paper #9

Closed Liyw979 closed 4 years ago

Liyw979 commented 4 years ago

This implementation is based on maskrcnn-benchmark, from which the faster rcnn is not the same in the original paper, for example 1 origin backbone: vgg16, here: resnet 2 origin roi pooler: roi pool, here: roi align 3 origin roi feature: 2 mlp, here ResNet50Conv5 and so on These difference is default in the maskrcnn-benchmark. People who refers to this implementation so really pay attention to these difference.

krumo commented 4 years ago

@liyiwei979621500 I totally agree with you. The setting used in the original paper (like VGG16 and roi pooling) is not popular anymore. I think it is rational to update the training/testing configurations in alignment with the state-of-the-art object detection framework. If you would like to run the DA Faster RCNN in the original setting, I would suggest you implement the necessary components by yourself or use the Caffe version or Caffe2 version of DA Faster RCNN. Both ways would be easy.